Seismic Risk Assessment Using AI Sampling for Existing Buildings
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for assessing seismic risk in large building stocks are time-consuming and costly, requiring extensive manual inspection and analysis by expert operators, and existing simplified methods still require examination of each building individually, leading to long performance times.
Innovation Solution
A method integrating conventional and rapid analysis with AI-based machine learning to create a statistical prediction model using a subset of buildings, applying a rapid qualitative analysis followed by a scientific quantitative analysis, and then using supervised learning to predict seismic vulnerability and risk for the entire stock.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional analysis method is applied to assess seismic risk of all buildings, then measurement precision is improved, but loss of time increases significantly
Solution Approach 1:
The patent divides the building stock into two groups: a sample group (25-33% of buildings) subjected to conventional detailed analysis, and a remaining group assessed through AI prediction models trained on the sample data. This segmentation allows high-precision assessment of a subset while using the learned patterns to rapidly assess the majority, resolving the contradiction between precision and time.
Solution Approach 2:
The patent creates a digital copy of the conventional analysis method in the form of an AI prediction model. The model learns from the sample buildings' characteristics and vulnerability parameters, then replicates the assessment results for the remaining buildings without performing actual physical inspections, thereby maintaining precision while dramatically reducing time.
2Ease of operation
If simplified expert judgment method is applied to all buildings, then ease of operation is improved, but loss of time increases
Solution Approach 1:
The patent replaces the manual mechanical process of expert operators systematically evaluating each building with an automated AI-based prediction system. The AI model processes building characteristics and outputs vulnerability assessments automatically, eliminating the time-consuming manual inspection while maintaining operational simplicity through automated decision-making.
3Measurement precision
If conventional analysis method is applied to large building stocks, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent extracts the essential patterns and relationships from the complex conventional analysis method and encapsulates them in the AI prediction model. By taking out the core analytical logic from the complex manual process, the system maintains measurement precision while reducing operational complexity through automated pattern recognition rather than complex step-by-step evaluations.
4Loss of time
If rapid analysis method is applied to all buildings, then loss of time is reduced, but measurement precision deteriorates
Solution Approach 1:
The patent implements a feedback mechanism where the AI prediction model is trained on the results from the sample group assessed with conventional methods. The model continuously refines its predictions based on the relationship between building characteristics and actual vulnerability, thereby improving measurement precision over time while maintaining rapid assessment speeds.
Data Source
AI summary
Method for assessing the seismic risk on existing buildings, comprising the following steps:a) identifying a set (N) of existing buildings to assess;b) acquiring for all existing buildings belonging to said set (N) qualitative data relating to the formal and construction features of said buildings;c) processing said qualitative data with a rapid analysis method based on qualitative criteria to assess the seismic vulnerability, and the related basic seismic risk, of all existing buildings belonging to the set (N);d) selecting in an organized manner a subset(S) comprising 25% to 33% of buildings of the set (N);e) acquiring for all the buildings of the subset(S) a plurality of analytical parameters;f) processing said plurality of analytical parameters with a scientific analysis method based on quantitative criteria to assess the vulnerability and the basic seismic risk of all the buildings of the subset(S);g) selecting in an organized manner a learning sample (A) comprising 70% to 80% of the buildings of the subset(S), and deriving by subtraction a verification sample (V) comprising 20% to 30% of buildings of the subset(S);h) using an AI-based machine learning model entering into an algorithm, for each building included in said learning sample (A), at least a part of said plurality of analytical parameters and the corresponding seismic vulnerability and basic seismic risk results already obtained with the scientific analysis method referred to in step f), to generate a statistical model for predicting seismic vulnerability and basic seismic risk universally applicable to any building in the set (N);i) applying said statistical prediction model to the buildings of the verification sample (V) using as input data the same part of said plurality of analytical parameters used for learning sample (A), and obtaining as output data calculated values of seismic vulnerability and basic seismic risk;l) comparing said values calculated as output from said statistical prediction model referred to in step i) with the corresponding values of seismic vulnerability and basic seismic risk obtained by applying the scientific analysis method referred to in step f), and determining a degree of accuracy, precision and sensitivity APS of the statistical prediction model;m) if said degree of APS has a value greater than a pre-established value, applying the same validated statistical prediction model to the remaining part of the buildings of the set (N) on which the scientific analysis method has not been applied;n) if said degree of APS has a value lower than said pre-established value, increasing the number of existing buildings belonging to the subset(S) and reiterating steps e) to l) until the statistical prediction model is validated.